Continuous camera placement using multiple objective optimisation process

Abstract

Most existing camera placement algorithms focus on coverage and/or visibility analysis, which ensures that the object of interest is visible in the camera's field of view (FOV). However, visibility is inadequate for continuous and automated tracking. In such applications, a sufficient overlap between FOVs should be secured so that camera handoff can be executed successfully and automatically before the object of interest becomes untraceable or unidentifiable. In addition, most of the existing algorithms employ discrete solution space, which suffers from limited solution accuracy and high computational complexity due to the high dimension of sampled solution space. In this paper, we propose to perform the optimisation of the camera parameters in a continuous solution space. In addition, to incorporate the optimisation of coverage and sufficient overlapped FOVs, a weighted sum approach is utilised to translate a multiple objective optimisation problem into a single objective optimisation process in our previous work. Significantly improved handoff success rates are illustrated via experiments using typical office floor plans in comparison with Erdem and Sclaroff's method. Improved accuracy, enhanced robustness, completeness of the solution set, and reduced computational complexity are accomplished in comparison with our previous algorithms.

Retracted: Gesture recognition algorithm based on multi‐scale feature fusion in RGB‐D images

“…The discrete form as shown in (4). Through histogram equalisation, the colour difference between the defective and non-defective parts is enhanced, thereby improving the contrast and helping to classify the model; then using random flips the matrix processes the data set to augment the data set.…”

“…The core idea of the vision-based gesture recognition method is the process of processing gesture images with appropriate methods, generating a predicted category result of gestures, and comparing the predicted result with the known classification result. The most suitable gesture recognition method can be selected according to different data types, influencing factors, types to be identified, so that recognition results with higher accuracy, robustness, and better real-time performance can be obtained [4]. Traditional vision-based gesture recognition methods mostly use RGB images acquired by a single camera or greyscale images and binary images processed from RGB images [5], which are generally restricted by ambient lighting, background complexity, and complexion.…”

Physical and cyber security in a smart grid environment

“…As a critical step, visibility analysis is used to calculate the observable area of a sensor based on its characteristics and the geographical features including topography, layout, vegetation, and buildings . A maximum effective distance should be set for each sensor.…”

“…For example, the rate of coverage and sufficient overlap between FOVs should be considered together. In Ref , a simple weighted sum of multiple objectives is used as the cost function. Although multiple objectives are considered, the selection of weighting factors remains an issue.…”

“…As a critical step, visibility analysis is used to calculate the observable area of a sensor based on its characteristics and the geographical features including topography, layout, vegetation, and buildings. 83 A maximum effective distance should be set for each sensor. Those areas that are beyond a distance threshold from the sensor are regarded as invisible even if they are within the sensor's FOV.…”